Score-Based Explanations in Data Management and Machine Learning

• URL: http://arxiv.org/abs/2007.12799v2
• Date: Wed, 19 Aug 2020 01:53:53 GMT
• Title: Score-Based Explanations in Data Management and Machine Learning
• Authors: Leopoldo Bertossi
• Abstract summary: We consider explanations for query answers in databases, and for results from classification models. The described approaches are mostly of a causal and counterfactual nature.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We describe some approaches to explanations for observed outcomes in data management and machine learning. They are based on the assignment of numerical scores to predefined and potentially relevant inputs. More specifically, we consider explanations for query answers in databases, and for results from classification models. The described approaches are mostly of a causal and counterfactual nature. We argue for the need to bring domain and semantic knowledge into score computations; and suggest some ways to do this.

Related papers

• Evaluating the Utility of Model Explanations for Model Development [54.23538543168767]
  We evaluate whether explanations can improve human decision-making in practical scenarios of machine learning model development. To our surprise, we did not find evidence of significant improvement on tasks when users were provided with any of the saliency maps. These findings suggest caution regarding the usefulness and potential for misunderstanding in saliency-based explanations.
  arXiv  Detail & Related papers  (2023-12-10T23:13:23Z)
• Attribution-Scores in Data Management and Explainable Machine Learning [0.0]
  We describe recent research on the use of actual causality in the definition of responsibility scores in databases. In the case of databases, useful connections with database repairs are illustrated and exploited. For classification models, the responsibility score is properly extended and illustrated.
  arXiv  Detail & Related papers  (2023-07-31T22:41:17Z)
• Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
  Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
  arXiv  Detail & Related papers  (2023-06-14T23:24:01Z)
• A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis [128.0532113800092]
  We present a mechanistic interpretation of Transformer-based LMs on arithmetic questions. This provides insights into how information related to arithmetic is processed by LMs.
  arXiv  Detail & Related papers  (2023-05-24T11:43:47Z)
• Attribution-Scores and Causal Counterfactuals as Explanations in Artificial Intelligence [0.0]
  We highlight the relevance of explanations for artificial intelligence, in general, and for the newer developments in em explainable AI We describe in simple terms, explanations in data management and machine learning that are based on attribution-scores, and counterfactuals as found in the area of causality.
  arXiv  Detail & Related papers  (2023-03-06T01:46:51Z)
• Explainable Data-Driven Optimization: From Context to Decision and Back Again [76.84947521482631]
  Data-driven optimization uses contextual information and machine learning algorithms to find solutions to decision problems with uncertain parameters. We introduce a counterfactual explanation methodology tailored to explain solutions to data-driven problems. We demonstrate our approach by explaining key problems in operations management such as inventory management and routing.
  arXiv  Detail & Related papers  (2023-01-24T15:25:16Z)
• Explainability in Process Outcome Prediction: Guidelines to Obtain Interpretable and Faithful Models [77.34726150561087]
  We define explainability through the interpretability of the explanations and the faithfulness of the explainability model in the field of process outcome prediction. This paper contributes a set of guidelines named X-MOP which allows selecting the appropriate model based on the event log specifications.
  arXiv  Detail & Related papers  (2022-03-30T05:59:50Z)
• Reasoning about Counterfactuals and Explanations: Problems, Results and Directions [0.0]
  These approaches are flexible and modular in that they allow the seamless addition of domain knowledge. The programs can be used to specify and compute responsibility-based numerical scores as attributive explanations for classification results.
  arXiv  Detail & Related papers  (2021-08-25T01:04:49Z)
• Score-Based Explanations in Data Management and Machine Learning: An Answer-Set Programming Approach to Counterfactual Analysis [0.0]
  We describe some recent approaches to score-based explanations for query answers in databases and outcomes from classification models in machine learning. Special emphasis is placed on declarative approaches based on answer-set programming to the use of counterfactual reasoning for score specification and computation.
  arXiv  Detail & Related papers  (2021-06-19T19:21:48Z)
• A Diagnostic Study of Explainability Techniques for Text Classification [52.879658637466605]
  We develop a list of diagnostic properties for evaluating existing explainability techniques. We compare the saliency scores assigned by the explainability techniques with human annotations of salient input regions to find relations between a model's performance and the agreement of its rationales with human ones.
  arXiv  Detail & Related papers  (2020-09-25T12:01:53Z)
• An ASP-Based Approach to Counterfactual Explanations for Classification [0.0]
  We propose answer-set programs that specify and compute counterfactual interventions as a basis for causality-based explanations to decisions produced by classification models. They can be applied with black-box models and models that can be specified as logic programs, such as rule-based classifiers.
  arXiv  Detail & Related papers  (2020-04-28T01:36:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.